search

unsky / FPN

Feature Pyramid Networks for Object Detection
522 stars 263 forks source link

训练好的caffemodel容量1.2G #79

Open SineXue opened 6 years ago

SineXue commented 6 years ago

得到的结果也没什么问题就是训练好的caffemodel很大，不明白为什么，求大神解答

unsky commented 6 years ago

FPN里面并没有太考虑模型的参数量，有大量的可优化空间，但不属于该论文的讨论范畴

SineXue commented 6 years ago

多谢解答，还有我想请问这个如果在fddb上面测试的话，修改tools/demo.py的一些内容可以正常进行吗，因为我在测试过程中遇到一些问题，麻烦你了

SineXue commented 6 years ago

已经解决了，多谢

mantou22 commented 5 years ago

when I run the demo.py,there is a problem,could you help me??????

Loaded network /home/xmpu234/Documents/FPN-caffe_1/data/faster_rcnn_models/fpn_iter_25000.caffemodel Traceback (most recent call last): File "/home/xmpu234/Documents/FPN-caffe1/tools/demo.py", line 142, in , _= im_detect(net, im) File "/home/xmpu234/Documents/FPN-caffe_1/tools/../lib/fast_rcnn/test.py", line 158, in im_detect rois2 = net.blobs['rpn_rois/p2'].data.copy() KeyError: 'rpn_rois/p2